Skip system attributes when applying mvdistinct stats

When estimating number of distinct groups, we failed to ignore system
attributes when matching the group expressions to mvdistinct stats,
causing failures like

  ERROR: negative bitmapset member not allowed

Fix that by simply skipping anything that is not a regular attribute.
Backpatch to PostgreSQL 10, where the extended stats were introduced.

Bug: #16111
Reported-by: Tuomas Leikola
Author: Tomas Vondra
Backpatch-through: 10
Discussion: https://postgr.es/m/16111-687799584c3a7e73@postgresql.org

3 files changed, 24 insertions, 5 deletions

diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index 35a8995f623..024f325eb02 100644
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -3582,14 +3582,19 @@ estimate_multivariate_ndistinct(PlannerInfo *root, RelOptInfo *rel,
 	foreach(lc, *varinfos)
 	{
 		GroupVarInfo *varinfo = (GroupVarInfo *) lfirst(lc);
+		AttrNumber	attnum;
 
 		Assert(varinfo->rel == rel);
 
-		if (IsA(varinfo->var, Var))
-		{
-			attnums = bms_add_member(attnums,
-									 ((Var *) varinfo->var)->varattno);
-		}
+		if (!IsA(varinfo->var, Var))
+			continue;
+
+		attnum = ((Var *) varinfo->var)->varattno;
+
+		if (!AttrNumberIsForUserDefinedAttr(attnum))
+			continue;
+
+		attnums = bms_add_member(attnums, attnum);
 	}
 
 	/* look for the ndistinct statistics matching the most vars */
@@ -3669,6 +3674,10 @@ estimate_multivariate_ndistinct(PlannerInfo *root, RelOptInfo *rel,
 			}
 
 			attnum = ((Var *) varinfo->var)->varattno;
+
+			if (!AttrNumberIsForUserDefinedAttr(attnum))
+				continue;
+
 			if (!bms_is_member(attnum, matched))
 				newlist = lappend(newlist, varinfo);
 		}
diff --git a/src/test/regress/expected/stats_ext.out b/src/test/regress/expected/stats_ext.out
index b65228fa07a..dfbc41c390d 100644
--- a/src/test/regress/expected/stats_ext.out
+++ b/src/test/regress/expected/stats_ext.out
@@ -233,6 +233,13 @@ SELECT s.stxkind, d.stxdndistinct
  {d,f,m} | {"3, 4": 11, "3, 6": 11, "4, 6": 11, "3, 4, 6": 11}
 (1 row)
 
+-- minor improvement, make sure the ctid does not break the matching
+SELECT * FROM check_estimated_rows('SELECT COUNT(*) FROM ndistinct GROUP BY ctid, a, b');
+ estimated | actual 
+-----------+--------
+        11 |   1000
+(1 row)
+
 -- Hash Aggregate, thanks to estimates improved by the statistic
 SELECT * FROM check_estimated_rows('SELECT COUNT(*) FROM ndistinct GROUP BY a, b');
  estimated | actual 
diff --git a/src/test/regress/sql/stats_ext.sql b/src/test/regress/sql/stats_ext.sql
index 040ee97a1e5..6237fb25c20 100644
--- a/src/test/regress/sql/stats_ext.sql
+++ b/src/test/regress/sql/stats_ext.sql
@@ -167,6 +167,9 @@ SELECT s.stxkind, d.stxdndistinct
  WHERE s.stxrelid = 'ndistinct'::regclass
    AND d.stxoid = s.oid;
 
+-- minor improvement, make sure the ctid does not break the matching
+SELECT * FROM check_estimated_rows('SELECT COUNT(*) FROM ndistinct GROUP BY ctid, a, b');
+
 -- Hash Aggregate, thanks to estimates improved by the statistic
 SELECT * FROM check_estimated_rows('SELECT COUNT(*) FROM ndistinct GROUP BY a, b');